Step 3.5 Flash 2603 API
About
Build advanced reasoning agents with Step 3.5 Flash 2603, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $0.10/1M input and $0.30/1M output tokens, native tool calling support, open weights architecture. Access Step 3.5 Flash 2603 via the EmpirioLabs AI API with up to 131K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
Yes
Structured Output
No
Tool Use
Yes
WeightsOpen
Limits
Context Window
256K
Tokens
Input Limit
256K
Tokens
Max Output
131K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.10
Output
$0.30
Caching (per 1M tokens)
Read
$0.02
Frequently Asked Questions
Step 3.5 Flash 2603 by EmpirioLabs AI costs $0.10 per 1M input tokens and $0.30 per 1M output tokens. Cached reads cost $0.02 per 1M tokens.
Model Details
ID
step-3-5-flash-2603
Provider
EmpirioLabs AIFamily
Release Date
Apr 2, 2026
Knowledge Cutoff
Jan 1, 2025
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
EMPIRIOLABS_API_KEY
API Base URL
https://api.empiriolabs.ai/v1